Label Refinement for Noisy Annotation in Weakly Supervised Segmentation

Ziyi Huang, Hongshan Liu, Haofeng Zhang, Fuyong Xing, Andrew Laine, Elsa Angelini, Christine Hendon, Yu Gan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep learning has revolutionized medical image analysis, promising to significantly improve the precision of diagnoses and therapies through advanced segmentation methods. However, the efficacy of deep neural networks is often compromised by the prevalence of imperfect medical labels, while acquiring large-scale, accurately labeled data remains a prohibitive challenge. To address the imperfect label issue, we introduce a novel learning framework that iteratively optimizes both a neural network and its label set to enhance segmentation accuracy. This framework operates through two steps: initially, it robustly trains on a dataset with label noise, distinguishing between clean and noisy labels, and subsequently, it refines noisy labels based on high-confidence predictions from the robust network. By applying this method, not only is the network trained more effectively on imperfect data, but the dataset is progressively cleaned and expanded. Our evaluations are conducted on retina Optical Coherence Tomography datasets using U-Net and SegNet architectures, and demonstrate substantial improvements in segmentation accuracy and data quality, advancing the capabilities of weakly supervised segmentation in medical imaging.

Original languageEnglish
Title of host publicationMedical Imaging 2024
Subtitle of host publicationImage Processing
EditorsOlivier Colliot, Jhimli Mitra
ISBN (Electronic)9781510671560
DOIs
StatePublished - 2024
EventMedical Imaging 2024: Image Processing - San Diego, United States
Duration: 19 Feb 202422 Feb 2024

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12926
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2024: Image Processing
Country/TerritoryUnited States
CitySan Diego
Period19/02/2422/02/24

Keywords

  • Deep Learning
  • Image Analysis
  • Label Refinement
  • Weakly Supervised Segmentation

Fingerprint

Dive into the research topics of 'Label Refinement for Noisy Annotation in Weakly Supervised Segmentation'. Together they form a unique fingerprint.

Cite this